Félix MalfaitandGitHub
21ff42074d
## Summary This PR introduces a Skills system for AI agents, inspired by the [Agent Skills specification](https://agentskills.io/specification). ## Changes ### Backend - **SkillEntity**: New database entity with migration for storing skills - **V2 Sync Mechanism**: Implemented FlatSkill, builders, validators, and action handlers following the v2 flat entity pattern - **Standard Skills**: Pre-defined skills (workflow-building, data-manipulation, dashboard-building, metadata-building, research, code-interpreter, xlsx, pdf, docx, pptx) - **GraphQL API**: CRUD operations for skills with proper guards and permissions - **Workspace Cache**: Integrated skills into the workspace cache system ### Frontend - **Skills Table**: Searchable table in AI settings showing all skills - **Skill Form**: Create/edit page with Label (primary), Description, and Content (markdown editor) - **API Name**: Following existing patterns, name is derived from label with advanced settings toggle for custom API names - **Standard vs Custom**: Standard skills are read-only, custom skills can be edited/deleted ## Key Design Decisions - Skills are stored in the database (Salesforce-like approach) rather than files - Name is derived from Label by default (isLabelSyncedWithName pattern) - Skills reference functions/files via @ mentions in markdown content rather than explicit relations - Standard skills are synced from code, custom skills are created via UI ## Screenshots Skills table and form UI follow existing settings patterns. ## Testing - [x] Lint passes - [x] Typecheck passes - [ ] CI tests
44 lines
1.6 KiB
TypeScript
44 lines
1.6 KiB
TypeScript
import {
|
|
type ActivateSkillFactoryInput,
|
|
activateSkillQueryFactory,
|
|
} from 'test/integration/metadata/suites/skill/utils/activate-skill-query-factory.util';
|
|
import { makeMetadataAPIRequest } from 'test/integration/metadata/suites/utils/make-metadata-api-request.util';
|
|
import { type CommonResponseBody } from 'test/integration/metadata/types/common-response-body.type';
|
|
import { type PerformMetadataQueryParams } from 'test/integration/metadata/types/perform-metadata-query.type';
|
|
import { warnIfErrorButNotExpectedToFail } from 'test/integration/metadata/utils/warn-if-error-but-not-expected-to-fail.util';
|
|
import { warnIfNoErrorButExpectedToFail } from 'test/integration/metadata/utils/warn-if-no-error-but-expected-to-fail.util';
|
|
|
|
import { type SkillDTO } from 'src/engine/metadata-modules/skill/dtos/skill.dto';
|
|
|
|
export const activateSkill = async ({
|
|
input,
|
|
gqlFields,
|
|
expectToFail = false,
|
|
token,
|
|
}: PerformMetadataQueryParams<ActivateSkillFactoryInput>): CommonResponseBody<{
|
|
activateSkill: SkillDTO;
|
|
}> => {
|
|
const graphqlOperation = activateSkillQueryFactory({
|
|
input,
|
|
gqlFields,
|
|
});
|
|
|
|
const response = await makeMetadataAPIRequest(graphqlOperation, token);
|
|
|
|
if (expectToFail === true) {
|
|
warnIfNoErrorButExpectedToFail({
|
|
response,
|
|
errorMessage: 'Skill activation should have failed but did not',
|
|
});
|
|
}
|
|
|
|
if (expectToFail === false) {
|
|
warnIfErrorButNotExpectedToFail({
|
|
response,
|
|
errorMessage: 'Skill activation has failed but should not',
|
|
});
|
|
}
|
|
|
|
return { data: response.body.data, errors: response.body.errors };
|
|
};
|